Development of voice and other interaction applications

Abstract

Among other things, a developer of an interaction application for an enterprise can create items of content to be provided to an assistant platform for use in responses to requests of end-users. The developer can deploy the interaction application using defined items of content and an available general interaction model including intents and sample utterances having slots. The developer can deploy the interaction application without requiring the developer to formulate any of the intents, sample utterances, or slots of the general interaction model.

The invention claimed is: 
     
       1. A machine-based method comprising
 presenting a user interface enabling a developer of an interaction application to select general utterance patterns for inclusion in the interaction application, each of the general utterance patterns spanning a set of one or more sample utterances that correspond to the general utterance pattern, the user interface exposing a set of available general utterance patterns, 
 automatically applying machine learning techniques to stored sample utterances, stored general utterance patterns, or sample utterances proposed by developers of interaction applications, to identify additional general utterance patterns, and 
 including the additional general utterance patterns in the set of available general utterance patterns exposed by the user interface. 
 
     
     
       2. The machine-based method of  claim 1  comprising
 matching proposed sample utterances of developers with stored sample utterances or stored general utterance patterns to identify the additional general utterance patterns. 
 
     
     
       3. The machine-based method of  claim 1  in which the interaction application is being developed for an enterprise of a particular industry, and at least some of the general utterance patterns are available to developers of interaction applications for another industry. 
     
     
       4. The machine-based method of  claim 1  comprising
 in response to the developer proposing a sample utterance for the interaction application, automatically suggesting inclusion in the interaction application of a particular general utterance pattern. 
 
     
     
       5. The machine-based method of  claim 1  comprising
 identifying additional general utterance patterns for inclusion in the set of available general utterance patterns based on similar sample utterances proposed by multiple developers of interaction applications for enterprises in a particular industry. 
 
     
     
       6. The machine-based method of  claim 1  comprising
 determining an intent of a sample utterance proposed by the developer; and 
 identifying a stored sample utterance or a stored general utterance pattern having an intent that matches the intent of the proposed sample utterance. 
 
     
     
       7. The machine-based method of  claim 6  comprising
 automatically suggesting a particular general utterance pattern for inclusion in the interaction application in response to determining that the intent of the proposed sample utterance does not match an intent of stored sample utterances or stored general utterance patterns. 
 
     
     
       8. The machine-based method of  claim 1  comprising
 identifying an industry for the interaction application based on a sample utterance proposed by the developer; and 
 identifying the additional general utterance patterns for inclusion in the set of available general utterance patterns based on the industry. 
 
     
     
       9. The machine-based method of  claim 1  comprising
 identifying an industry for a sample utterance proposed by the developer; and 
 automatically suggesting inclusion of the sample utterance to one or more other developers of interaction applications in the industry. 
 
     
     
       10. The machine-based method of  claim 9  comprising
 applying the machine learning techniques to the sample utterance proposed by the developer to identify the industry. 
 
     
     
       11. The machine-based method of  claim 9  comprising
 training the machine learning techniques for interaction applications in the industry using the proposed sample utterance. 
 
     
     
       12. The machine-based method of  claim 1  comprising
 forming the interaction application including at least one of the additional general utterance patters. 
 
     
     
       13. The machine-based method of  claim 12  comprising deploying the interaction application.